at_code_wizard's profile picture. @cognition_labs | @StanfordAILab

Moritz Stephan

@at_code_wizard

@cognition_labs | @StanfordAILab

had some cool runs this week where Devin successfully debugged fullstack changes – getting a video demo of the change is awesome

at_code_wizard's tweet image. had some cool runs this week where Devin successfully debugged fullstack changes – getting a video demo of the change is awesome

Devin now has full computer use capabilities and can share screen recordings. You can control desktop apps, build and QA mobile apps, and automate tedious work. Here are some examples that blew our team away: 1. Making a desktop game



gpus go brrrr

Today we’re releasing SWE-1.5, our fast agent model. It achieves near-SOTA coding performance while setting a new standard for speed. Now available in @windsurf.

cognition's tweet image. Today we’re releasing SWE-1.5, our fast agent model.

It achieves near-SOTA coding performance while setting a new standard for speed. Now available in @windsurf.


Congrats on the launch! Collaborating with @applied_compute over the past few months has been incredible. Building agents that perform at the top of their class takes deep expertise – not just in RL, but also in the domains you’re solving for. Exciting to see @ypatil125 @rhythmrg

Generalists are useful, but it’s not enough to be smart. Advances come from specialists, whether human or machine. To have an edge, agents need specific expertise, within specific companies, built on models trained on specific data. We call this Specific Intelligence. It's…

appliedcompute's tweet image. Generalists are useful, but it’s not enough to be smart.

Advances come from specialists, whether human or machine.

To have an edge, agents need specific expertise, within specific companies, built on models trained on specific data.

We call this Specific Intelligence.

It's…


there's a discrete speed threshold that separates "sync" and "async" coding agent experiences. SWE-grep/SWE-grep-mini are pushing the pareto of what's possible below this line, so you can get more done faster while remaining in flow

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!



decided to add my prompt snippets to the product

at_code_wizard's tweet image. decided to add my prompt snippets to the product

When using Sonnet 4.5 in Devin (probably works in other agents too?), I found it surprisingly effective to just add "when you're done, self-critique your work until you're sure it's correct". Had a few cool cases where it caught issues I would have flagged in a first pass review…



every windsurfer needs a lifeguard... 🛟

at_code_wizard's tweet image. every windsurfer needs a lifeguard... 🛟

Moritz Stephan reposted

Been adding this to every task and it really does make a difference

When using Sonnet 4.5 in Devin (probably works in other agents too?), I found it surprisingly effective to just add "when you're done, self-critique your work until you're sure it's correct". Had a few cool cases where it caught issues I would have flagged in a first pass review…



When using Sonnet 4.5 in Devin (probably works in other agents too?), I found it surprisingly effective to just add "when you're done, self-critique your work until you're sure it's correct". Had a few cool cases where it caught issues I would have flagged in a first pass review…


merged first first Devin PR of the day in the uber ✅


Klyra mode

Trade Anywhere, Instantly. The widest range of assets from one account. No margin or positions micromanaging, pure execution. This is how trading should be. This is how you Trade to Win. klyra.com



sonnet 4.5 feels like the biggest qualitative jump since the newer sonnet 3.5 came out. I've been using it for the last few days in Devin & found some new behaviors I haven't seen in other models: - can manage it's own context well -> it starts to write down notes in markdown…

We rebuilt Devin for Claude Sonnet 4.5. Available starting today as an Agent Preview that’s over 2x faster and 12% better on our Jr. Developer Evals.



🚢

Wave 12 is here, and it’s a big one! 📚 DeepWiki-powered docs for every symbol in your codebase 🔍 Vibe and Replace 🐛 100+ bugs squashed 🎨 Brand new UI … and more! Everything that’s new 🧵



Try gpt-5 in Devin!

We’ve been working closely with the @OpenAI team to integrate GPT-5 into Devin. Starting today, you can select a preview version of Devin that uses GPT-5 as part of our agent orchestration. GPT-5 eval results 👇



Very excited about the launch of ryan-100T-2025-07-28. Given the positive results in early testing, we think this massive 18 year training run is just scratching the surface of what’s possible

Cognition is the first AI lab to win a verified gold medal at the IOI. Our human, ryanbAI (@ryanbai1412), placed 7th overall. Impressively, ryanbAI competed under the exact same conditions as all human contestants.

que_tourist's tweet image. Cognition is the first AI lab to win a verified gold medal at the IOI. Our human, ryanbAI (@ryanbai1412), placed 7th overall. Impressively, ryanbAI competed under the exact same conditions as all human contestants.
que_tourist's tweet image. Cognition is the first AI lab to win a verified gold medal at the IOI. Our human, ryanbAI (@ryanbai1412), placed 7th overall. Impressively, ryanbAI competed under the exact same conditions as all human contestants.


Bullish

3 patent filings, 20+ granted design rights, and 2500+ Onshape commits. Like SpaceX, we developed every component from scratch = 90% cost savings. Built in a few months by 3 engineers locked in a room with no sunlight in the middle of London. Stress-tested daily in a live…



This is crazy

Qwen3-Coder at ~2000 tokens/sec is now live in Windsurf! ⚡️ Fully hosted on US servers by @CerebrasSystems. Video is 1x speed.



Welcome on board @premqnair !

I’ve joined Cognition to continue to work on the future of software engineering. I was employee #2 at Windsurf and have worked on AI+code for years. There’s never been a more exciting time and place for it than now at Cognition. I had a place at Google DeepMind as part of the…



software engineering is so much more than just coding

MCP is here! You can now give Devin access to your favorite servers via the MCP Marketplace. Think Datadog, Linear, Sentry, Figma, and thousands more. Demos from our team + getting started 👇



Moritz Stephan reposted

Devin: First to do real merged PRs Devin: Also first to do real AI merger 🔥


lfg 🚀

Cognition has signed a definitive agreement to acquire Windsurf. The acquisition includes Windsurf’s IP, product, trademark and brand, and strong business. Above all, it includes Windsurf’s world-class people, whom we’re privileged to welcome to our team. We are also honoring…



United States Trends

Loading...

Something went wrong.


Something went wrong.